Análisis de modelos SOM - Frecuencia datos de entrada: mes

Modelo

• ID: 283
• Descripción:
• Frecuencia: mes
• Variables: fecha_cnt, precip, longitud, latitud, altitud
• Dimensiones del mapa: 10,10
• Iteraciones: 1000
• Parámetros adicionales:

source("../../lib/som-utils.R")

Attaching package: 'dplyr'

The following objects are masked from 'package:stats':

    filter, lag

The following objects are masked from 'package:base':

    intersect, setdiff, setequal, union

source("../../lib/maps-utils.R")

Linking to GEOS 3.8.0, GDAL 3.0.4, PROJ 6.3.1

Carga del modelo desde disco

mpr.set_base_path_analysis()
model <- mpr.load_model("som-283.rds.xz")
summary(model)

SOM of size 10x10 with a hexagonal topology and a bubble neighbourhood function.
The number of data layers is 1.
Distance measure(s) used: sumofsquares.
Training data included: 94881 objects.
Mean distance to the closest unit in the map: 0.348.

plot(model, type="changes")

Carga del dataset de entrada

df <- mpr.load_data("datos_mes.csv.xz")

df

summary(df)

 id_estacion           fecha             fecha_cnt           tmax      
 Length:94881       Length:94881       Min.   : 1.000   Min.   :-53.0  
 Class :character   Class :character   1st Qu.: 4.000   1st Qu.:148.0  
 Mode  :character   Mode  :character   Median : 6.000   Median :198.0  
                                       Mean   : 6.497   Mean   :200.2  
                                       3rd Qu.: 9.000   3rd Qu.:255.0  
                                       Max.   :12.000   Max.   :403.0  
      tmin             precip           nevada           prof_nieve      
 Min.   :-121.00   Min.   :  0.00   Min.   :0.000000   Min.   :   0.000  
 1st Qu.:  53.00   1st Qu.:  3.00   1st Qu.:0.000000   1st Qu.:   0.000  
 Median :  98.00   Median : 10.00   Median :0.000000   Median :   0.000  
 Mean   :  98.86   Mean   : 16.25   Mean   :0.000295   Mean   :   0.467  
 3rd Qu.: 148.00   3rd Qu.: 22.00   3rd Qu.:0.000000   3rd Qu.:   0.000  
 Max.   : 254.00   Max.   :422.00   Max.   :6.000000   Max.   :1834.000  
    longitud        latitud            altitud      
 Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.:38.28   1st Qu.: -5.6417   1st Qu.:  42.0  
 Median :40.82   Median : -3.4500   Median : 247.0  
 Mean   :39.66   Mean   : -3.4350   Mean   : 418.5  
 3rd Qu.:42.08   3rd Qu.:  0.4914   3rd Qu.: 656.0  
 Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

Carga de los mapas

world <- ne_countries(scale = "medium", returnclass = "sf")
spain <- subset(world, admin == "Spain")

Mapa de densidad

plot(model, type="count", shape = "straight", palette.name = mpr.degrade.bleu)

Número de elementos en cada celda:

nb <- table(model$unit.classif)
print(nb)

   1    2    3    4    5    6    7    8    9   10   11   12   13   14   15   16 
 442  635  805  928 1623 1022  705  363  263  496  180  722  844  833  667 1775 
  17   18   19   20   21   22   23   24   25   26   27   28   29   30   31   32 
1271  798  968  758  302  658  524  998  658 1491 1666 1575 1069  448  293  600 
  33   34   35   36   37   38   39   40   41   42   43   44   45   46   47   48 
 824 1425 1119  785  883 1707 1776 1473  972  571 1850 1235  988  252  484 1490 
  49   50   51   52   53   54   55   56   57   58   59   60   61   62   63   64 
1675 1089 1395 1020  434 1158 1394 1289  974 1006  732 1240 1883 1777  379 1580 
  65   66   67   68   69   70   71   72   73   74   75   76   77   78   79   80 
1868 1093 1117  780  902  518 1564 1648 2487  412 1348 1013  753  742  686  745 
  81   82   83   84   85   86   87   88   89   90   91   92   93   94   95   96 
 354 1002 1344  372 1400  872  714  506  264  175 1188  238  172  466 1574 1619 
  97   98   99  100 
 899  456  314   37 

Comprobación de nodos vacíos:

dim_model <- 10*10;
len_nb = length(nb);
empty_nodes <- dim_model != len_nb;
if (empty_nodes) {
  print(paste("[Warning] Existen nodos vacíos: ", len_nb, "/", dim_model))
}

Mapa de distancia entre vecinos

plot(model, type="dist.neighbours", shape = "straight")

Influencia de las variables

model_colnames = c("fecha_cnt", "precip", "longitud", "latitud", "altitud")
model_ncol = length(model_colnames)

Mapa de variables.

plot(model, shape = "straight")

Mapa de calor por variable

par(mfrow=c(3,4))
for (j in 1:model_ncol) {
  plot(model, type="property", property=getCodes(model,1)[,j],
    palette.name=mpr.coolBlueHotRed,
    main=model_colnames[j],
    cex=0.5, shape = "straight")
}

Correlación para cada columna del vector de nodos

if (!empty_nodes) {
  cor <- apply(getCodes(model,1), 2, mpr.weighted.correlation, w=nb, som=model)
  print(cor)
}

     fecha_cnt      precip   longitud    latitud    altitud
[1,] 0.4537281  0.10406448  0.5800066  0.3104531  0.4304931
[2,] 0.6136018 -0.06943821 -0.3970454 -0.1187163 -0.3779586

Representación de cada variable en un mapa de factores:

if (!empty_nodes) {
  par(mfrow=c(1,1))
  plot(cor[1,], cor[2,], xlim=c(-1,1), ylim=c(-1,1), type="n")
  lines(c(-1,1),c(0,0))
  lines(c(0,0),c(-1,1))
  text(cor[1,], cor[2,], labels=model_colnames, cex=0.75)
  symbols(0,0,circles=1,inches=F,add=T)
}

Importancia de cada variable - varianza ponderada por el tamaño de la celda:

if (!empty_nodes) {
  sigma2 <- sqrt(apply(getCodes(model,1),2,function(x,effectif)
     {m<-sum(effectif*(x-weighted.mean(x,effectif))^2)/(sum(effectif)-1)},
     effectif=nb))
  print(sort(sigma2,decreasing=T))
}

 longitud   latitud   altitud fecha_cnt    precip 
0.9798727 0.9719220 0.9695892 0.9519645 0.9439548 

Clustering

if (!empty_nodes) {
  hac <- mpr.hac(model, nb)
}

Visualización de 3 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=3)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=3)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax            tmin            precip           nevada 
 Min.   : 1.000   Min.   : -8.0   Min.   :-58.00   Min.   : 34.00   Min.   :0  
 1st Qu.: 3.000   1st Qu.:131.0   1st Qu.: 60.00   1st Qu.: 49.00   1st Qu.:0  
 Median : 9.000   Median :157.0   Median : 82.00   Median : 59.00   Median :0  
 Mean   : 7.381   Mean   :163.2   Mean   : 85.92   Mean   : 67.26   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:191.5   3rd Qu.:110.00   3rd Qu.: 76.00   3rd Qu.:0  
 Max.   :12.000   Max.   :350.0   Max.   :223.00   Max.   :422.00   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   :  0.0000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:  0.0000   1st Qu.:40.79   1st Qu.: -6.350   1st Qu.:  32.0  
 Median :  0.0000   Median :42.34   Median : -3.819   Median :  98.0  
 Mean   :  0.2192   Mean   :41.48   Mean   : -3.628   Mean   : 214.5  
 3rd Qu.:  0.0000   3rd Qu.:43.31   3rd Qu.: -1.636   3rd Qu.: 336.0  
 Max.   :607.0000   Max.   :43.57   Max.   :  4.216   Max.   :2400.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt           tmax            tmin             precip      
 Min.   : 1.000   Min.   :-53.0   Min.   :-121.00   Min.   :  0.00  
 1st Qu.: 4.000   1st Qu.:149.0   1st Qu.:  49.00   1st Qu.:  3.00  
 Median : 6.000   Median :198.0   Median :  95.00   Median : 10.00  
 Mean   : 6.429   Mean   :201.6   Mean   :  95.49   Mean   : 13.17  
 3rd Qu.: 9.000   3rd Qu.:259.0   3rd Qu.: 144.00   3rd Qu.: 20.00  
 Max.   :12.000   Max.   :403.0   Max.   : 254.00   Max.   :135.00  
     nevada           prof_nieve           longitud        latitud        
 Min.   :0.000000   Min.   :   0.0000   Min.   :28.31   Min.   :-16.4992  
 1st Qu.:0.000000   1st Qu.:   0.0000   1st Qu.:38.95   1st Qu.: -4.8458  
 Median :0.000000   Median :   0.0000   Median :40.95   Median : -2.4831  
 Mean   :0.000342   Mean   :   0.5223   Mean   :40.48   Mean   : -2.3604  
 3rd Qu.:0.000000   3rd Qu.:   0.0000   3rd Qu.:42.08   3rd Qu.:  0.5356  
 Max.   :6.000000   Max.   :1834.0000   Max.   :43.57   Max.   :  4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  44.0  
 Median : 263.0  
 Mean   : 425.6  
 3rd Qu.: 674.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt           tmax            tmin           precip            nevada 
 Min.   : 1.000   Min.   : 13.0   Min.   :-33.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 4.000   1st Qu.:201.0   1st Qu.:132.0   1st Qu.:  0.000   1st Qu.:0  
 Median : 7.000   Median :225.0   Median :160.0   Median :  1.000   Median :0  
 Mean   : 6.505   Mean   :217.4   Mean   :150.6   Mean   :  6.999   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:253.0   3rd Qu.:190.0   3rd Qu.:  8.000   3rd Qu.:0  
 Max.   :12.000   Max.   :356.0   Max.   :244.0   Max.   :114.000   Max.   :0  
   prof_nieve          longitud        latitud          altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.89   Min.   :  14.0  
 1st Qu.: 0.00000   1st Qu.:28.31   1st Qu.:-16.50   1st Qu.:  25.0  
 Median : 0.00000   Median :28.44   Median :-16.33   Median :  35.0  
 Mean   : 0.03084   Mean   :28.37   Mean   :-16.05   Mean   : 518.3  
 3rd Qu.: 0.00000   3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.: 632.0  
 Max.   :46.00000   Max.   :28.95   Max.   :-13.60   Max.   :2371.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

Visualización de 4 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=4)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=4)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax            tmin            precip           nevada 
 Min.   : 1.000   Min.   : -8.0   Min.   :-58.00   Min.   : 34.00   Min.   :0  
 1st Qu.: 3.000   1st Qu.:131.0   1st Qu.: 60.00   1st Qu.: 49.00   1st Qu.:0  
 Median : 9.000   Median :157.0   Median : 82.00   Median : 59.00   Median :0  
 Mean   : 7.381   Mean   :163.2   Mean   : 85.92   Mean   : 67.26   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:191.5   3rd Qu.:110.00   3rd Qu.: 76.00   3rd Qu.:0  
 Max.   :12.000   Max.   :350.0   Max.   :223.00   Max.   :422.00   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   :  0.0000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:  0.0000   1st Qu.:40.79   1st Qu.: -6.350   1st Qu.:  32.0  
 Median :  0.0000   Median :42.34   Median : -3.819   Median :  98.0  
 Mean   :  0.2192   Mean   :41.48   Mean   : -3.628   Mean   : 214.5  
 3rd Qu.:  0.0000   3rd Qu.:43.31   3rd Qu.: -1.636   3rd Qu.: 336.0  
 Max.   :607.0000   Max.   :43.57   Max.   :  4.216   Max.   :2400.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt           tmax            tmin             precip     
 Min.   : 1.000   Min.   : -4.0   Min.   :-110.00   Min.   : 0.00  
 1st Qu.: 4.000   1st Qu.:152.0   1st Qu.:  52.00   1st Qu.: 3.00  
 Median : 6.000   Median :201.0   Median :  97.00   Median : 9.00  
 Mean   : 6.427   Mean   :205.5   Mean   :  98.23   Mean   :12.45  
 3rd Qu.: 9.000   3rd Qu.:262.0   3rd Qu.: 145.00   3rd Qu.:19.00  
 Max.   :12.000   Max.   :403.0   Max.   : 254.00   Max.   :87.00  
     nevada           prof_nieve          longitud        latitud       
 Min.   :0.000000   Min.   : 0.00000   Min.   :35.28   Min.   :-8.6494  
 1st Qu.:0.000000   1st Qu.: 0.00000   1st Qu.:38.95   1st Qu.:-4.8500  
 Median :0.000000   Median : 0.00000   Median :40.93   Median :-2.4831  
 Mean   :0.000354   Mean   : 0.04781   Mean   :40.43   Mean   :-2.4232  
 3rd Qu.:0.000000   3rd Qu.: 0.00000   3rd Qu.:41.98   3rd Qu.: 0.4914  
 Max.   :6.000000   Max.   :75.00000   Max.   :43.57   Max.   : 4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  44.0  
 Median : 251.0  
 Mean   : 368.4  
 3rd Qu.: 656.0  
 Max.   :1971.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax             tmin             precip      
 Min.   : 1.00   Min.   :-53.00   Min.   :-121.00   Min.   :  0.00  
 1st Qu.: 4.00   1st Qu.: 29.00   1st Qu.: -33.00   1st Qu.: 17.00  
 Median : 6.00   Median : 73.00   Median :   6.00   Median : 30.00  
 Mean   : 6.51   Mean   : 82.95   Mean   :  12.65   Mean   : 34.91  
 3rd Qu.:10.00   3rd Qu.:133.00   3rd Qu.:  58.00   3rd Qu.: 48.00  
 Max.   :12.00   Max.   :263.00   Max.   : 148.00   Max.   :135.00  
     nevada    prof_nieve         longitud        latitud        
 Min.   :0   Min.   :   0.00   Min.   :28.31   Min.   :-16.4992  
 1st Qu.:0   1st Qu.:   0.00   1st Qu.:40.78   1st Qu.: -4.0103  
 Median :0   Median :   0.00   Median :42.38   Median :  0.8842  
 Mean   :0   Mean   :  14.85   Mean   :41.91   Mean   : -0.4648  
 3rd Qu.:0   3rd Qu.:   0.00   3rd Qu.:42.53   3rd Qu.:  1.3656  
 Max.   :0   Max.   :1834.00   Max.   :42.77   Max.   :  2.4378  
    altitud    
 Min.   :1167  
 1st Qu.:1894  
 Median :2228  
 Mean   :2152  
 3rd Qu.:2316  
 Max.   :2535  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt           tmax            tmin           precip            nevada 
 Min.   : 1.000   Min.   : 13.0   Min.   :-33.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 4.000   1st Qu.:201.0   1st Qu.:132.0   1st Qu.:  0.000   1st Qu.:0  
 Median : 7.000   Median :225.0   Median :160.0   Median :  1.000   Median :0  
 Mean   : 6.505   Mean   :217.4   Mean   :150.6   Mean   :  6.999   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:253.0   3rd Qu.:190.0   3rd Qu.:  8.000   3rd Qu.:0  
 Max.   :12.000   Max.   :356.0   Max.   :244.0   Max.   :114.000   Max.   :0  
   prof_nieve          longitud        latitud          altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.89   Min.   :  14.0  
 1st Qu.: 0.00000   1st Qu.:28.31   1st Qu.:-16.50   1st Qu.:  25.0  
 Median : 0.00000   Median :28.44   Median :-16.33   Median :  35.0  
 Mean   : 0.03084   Mean   :28.37   Mean   :-16.05   Mean   : 518.3  
 3rd Qu.: 0.00000   3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.: 632.0  
 Max.   :46.00000   Max.   :28.95   Max.   :-13.60   Max.   :2371.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

Visualización de 5 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=5)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=5)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax            tmin            precip           nevada 
 Min.   : 1.000   Min.   : 50.0   Min.   :-30.00   Min.   : 34.00   Min.   :0  
 1st Qu.: 3.000   1st Qu.:133.0   1st Qu.: 60.00   1st Qu.: 48.00   1st Qu.:0  
 Median : 9.000   Median :159.0   Median : 83.00   Median : 58.00   Median :0  
 Mean   : 7.442   Mean   :164.9   Mean   : 86.71   Mean   : 61.92   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:193.0   3rd Qu.:111.00   3rd Qu.: 72.00   3rd Qu.:0  
 Max.   :12.000   Max.   :336.0   Max.   :219.00   Max.   :125.00   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   : 0.00000   Min.   :28.48   Min.   :-17.755   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:40.71   1st Qu.: -6.056   1st Qu.:  32.0  
 Median : 0.00000   Median :42.33   Median : -3.799   Median :  95.0  
 Mean   : 0.06001   Mean   :41.48   Mean   : -3.428   Mean   : 205.2  
 3rd Qu.: 0.00000   3rd Qu.:43.31   3rd Qu.: -1.033   3rd Qu.: 334.5  
 Max.   :35.00000   Max.   :43.57   Max.   :  4.216   Max.   :1405.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt           tmax            tmin             precip     
 Min.   : 1.000   Min.   : -4.0   Min.   :-110.00   Min.   : 0.00  
 1st Qu.: 4.000   1st Qu.:152.0   1st Qu.:  52.00   1st Qu.: 3.00  
 Median : 6.000   Median :201.0   Median :  97.00   Median : 9.00  
 Mean   : 6.427   Mean   :205.5   Mean   :  98.23   Mean   :12.45  
 3rd Qu.: 9.000   3rd Qu.:262.0   3rd Qu.: 145.00   3rd Qu.:19.00  
 Max.   :12.000   Max.   :403.0   Max.   : 254.00   Max.   :87.00  
     nevada           prof_nieve          longitud        latitud       
 Min.   :0.000000   Min.   : 0.00000   Min.   :35.28   Min.   :-8.6494  
 1st Qu.:0.000000   1st Qu.: 0.00000   1st Qu.:38.95   1st Qu.:-4.8500  
 Median :0.000000   Median : 0.00000   Median :40.93   Median :-2.4831  
 Mean   :0.000354   Mean   : 0.04781   Mean   :40.43   Mean   :-2.4232  
 3rd Qu.:0.000000   3rd Qu.: 0.00000   3rd Qu.:41.98   3rd Qu.: 0.4914  
 Max.   :6.000000   Max.   :75.00000   Max.   :43.57   Max.   : 4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  44.0  
 Median : 251.0  
 Mean   : 368.4  
 3rd Qu.: 656.0  
 Max.   :1971.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax             tmin             precip      
 Min.   : 1.00   Min.   :-53.00   Min.   :-121.00   Min.   :  0.00  
 1st Qu.: 4.00   1st Qu.: 29.00   1st Qu.: -33.00   1st Qu.: 17.00  
 Median : 6.00   Median : 73.00   Median :   6.00   Median : 30.00  
 Mean   : 6.51   Mean   : 82.95   Mean   :  12.65   Mean   : 34.91  
 3rd Qu.:10.00   3rd Qu.:133.00   3rd Qu.:  58.00   3rd Qu.: 48.00  
 Max.   :12.00   Max.   :263.00   Max.   : 148.00   Max.   :135.00  
     nevada    prof_nieve         longitud        latitud        
 Min.   :0   Min.   :   0.00   Min.   :28.31   Min.   :-16.4992  
 1st Qu.:0   1st Qu.:   0.00   1st Qu.:40.78   1st Qu.: -4.0103  
 Median :0   Median :   0.00   Median :42.38   Median :  0.8842  
 Mean   :0   Mean   :  14.85   Mean   :41.91   Mean   : -0.4648  
 3rd Qu.:0   3rd Qu.:   0.00   3rd Qu.:42.53   3rd Qu.:  1.3656  
 Max.   :0   Max.   :1834.00   Max.   :42.77   Max.   :  2.4378  
    altitud    
 Min.   :1167  
 1st Qu.:1894  
 Median :2228  
 Mean   :2152  
 3rd Qu.:2316  
 Max.   :2535  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt           tmax            tmin            precip          nevada 
 Min.   : 1.000   Min.   : -8.0   Min.   :-58.00   Min.   :104.0   Min.   :0  
 1st Qu.: 2.000   1st Qu.:116.8   1st Qu.: 51.00   1st Qu.:122.8   1st Qu.:0  
 Median : 6.000   Median :133.0   Median : 72.00   Median :135.5   Median :0  
 Mean   : 6.477   Mean   :139.3   Mean   : 74.29   Mean   :146.2   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:158.2   3rd Qu.: 95.00   3rd Qu.:154.2   3rd Qu.:0  
 Max.   :12.000   Max.   :350.0   Max.   :223.00   Max.   :422.0   Max.   :0  
   prof_nieve         longitud        latitud           altitud      
 Min.   :  0.000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:41.89   1st Qu.: -8.624   1st Qu.:  58.0  
 Median :  0.000   Median :42.43   Median : -8.411   Median : 261.0  
 Mean   :  2.574   Mean   :41.48   Mean   : -6.594   Mean   : 352.7  
 3rd Qu.:  0.000   3rd Qu.:42.89   3rd Qu.: -4.010   3rd Qu.: 370.0  
 Max.   :607.000   Max.   :43.57   Max.   :  2.827   Max.   :2400.0  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt           tmax            tmin           precip            nevada 
 Min.   : 1.000   Min.   : 13.0   Min.   :-33.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 4.000   1st Qu.:201.0   1st Qu.:132.0   1st Qu.:  0.000   1st Qu.:0  
 Median : 7.000   Median :225.0   Median :160.0   Median :  1.000   Median :0  
 Mean   : 6.505   Mean   :217.4   Mean   :150.6   Mean   :  6.999   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:253.0   3rd Qu.:190.0   3rd Qu.:  8.000   3rd Qu.:0  
 Max.   :12.000   Max.   :356.0   Max.   :244.0   Max.   :114.000   Max.   :0  
   prof_nieve          longitud        latitud          altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.89   Min.   :  14.0  
 1st Qu.: 0.00000   1st Qu.:28.31   1st Qu.:-16.50   1st Qu.:  25.0  
 Median : 0.00000   Median :28.44   Median :-16.33   Median :  35.0  
 Mean   : 0.03084   Mean   :28.37   Mean   :-16.05   Mean   : 518.3  
 3rd Qu.: 0.00000   3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.: 632.0  
 Max.   :46.00000   Max.   :28.95   Max.   :-13.60   Max.   :2371.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

Visualización de 6 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=6)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=6)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax            tmin            precip           nevada 
 Min.   : 1.000   Min.   : 50.0   Min.   :-30.00   Min.   : 34.00   Min.   :0  
 1st Qu.: 3.000   1st Qu.:133.0   1st Qu.: 60.00   1st Qu.: 48.00   1st Qu.:0  
 Median : 9.000   Median :159.0   Median : 83.00   Median : 58.00   Median :0  
 Mean   : 7.442   Mean   :164.9   Mean   : 86.71   Mean   : 61.92   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:193.0   3rd Qu.:111.00   3rd Qu.: 72.00   3rd Qu.:0  
 Max.   :12.000   Max.   :336.0   Max.   :219.00   Max.   :125.00   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   : 0.00000   Min.   :28.48   Min.   :-17.755   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:40.71   1st Qu.: -6.056   1st Qu.:  32.0  
 Median : 0.00000   Median :42.33   Median : -3.799   Median :  95.0  
 Mean   : 0.06001   Mean   :41.48   Mean   : -3.428   Mean   : 205.2  
 3rd Qu.: 0.00000   3rd Qu.:43.31   3rd Qu.: -1.033   3rd Qu.: 334.5  
 Max.   :35.00000   Max.   :43.57   Max.   :  4.216   Max.   :1405.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax            tmin            precip     
 Min.   :1.000   Min.   : -4.0   Min.   :-89.00   Min.   : 0.00  
 1st Qu.:2.000   1st Qu.:128.0   1st Qu.: 28.00   1st Qu.: 5.00  
 Median :3.000   Median :161.0   Median : 61.00   Median :14.00  
 Mean   :2.865   Mean   :161.5   Mean   : 60.56   Mean   :15.92  
 3rd Qu.:4.000   3rd Qu.:191.0   3rd Qu.: 91.00   3rd Qu.:24.00  
 Max.   :9.000   Max.   :355.0   Max.   :236.00   Max.   :87.00  
     nevada           prof_nieve          longitud        latitud      
 Min.   :0.000000   Min.   : 0.00000   Min.   :35.28   Min.   :-8.649  
 1st Qu.:0.000000   1st Qu.: 0.00000   1st Qu.:38.95   1st Qu.:-5.289  
 Median :0.000000   Median : 0.00000   Median :40.95   Median :-2.331  
 Mean   :0.000662   Mean   : 0.09857   Mean   :40.50   Mean   :-2.308  
 3rd Qu.:0.000000   3rd Qu.: 0.00000   3rd Qu.:42.08   3rd Qu.: 0.595  
 Max.   :6.000000   Max.   :75.00000   Max.   :43.57   Max.   : 4.216  
    altitud      
 Min.   :   1.0  
 1st Qu.:  44.0  
 Median : 192.0  
 Mean   : 355.1  
 3rd Qu.: 628.0  
 Max.   :1668.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax             tmin             precip      
 Min.   : 1.00   Min.   :-53.00   Min.   :-121.00   Min.   :  0.00  
 1st Qu.: 4.00   1st Qu.: 29.00   1st Qu.: -33.00   1st Qu.: 17.00  
 Median : 6.00   Median : 73.00   Median :   6.00   Median : 30.00  
 Mean   : 6.51   Mean   : 82.95   Mean   :  12.65   Mean   : 34.91  
 3rd Qu.:10.00   3rd Qu.:133.00   3rd Qu.:  58.00   3rd Qu.: 48.00  
 Max.   :12.00   Max.   :263.00   Max.   : 148.00   Max.   :135.00  
     nevada    prof_nieve         longitud        latitud        
 Min.   :0   Min.   :   0.00   Min.   :28.31   Min.   :-16.4992  
 1st Qu.:0   1st Qu.:   0.00   1st Qu.:40.78   1st Qu.: -4.0103  
 Median :0   Median :   0.00   Median :42.38   Median :  0.8842  
 Mean   :0   Mean   :  14.85   Mean   :41.91   Mean   : -0.4648  
 3rd Qu.:0   3rd Qu.:   0.00   3rd Qu.:42.53   3rd Qu.:  1.3656  
 Max.   :0   Max.   :1834.00   Max.   :42.77   Max.   :  2.4378  
    altitud    
 Min.   :1167  
 1st Qu.:1894  
 Median :2228  
 Mean   :2152  
 3rd Qu.:2316  
 Max.   :2535  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt           tmax            tmin            precip          nevada 
 Min.   : 1.000   Min.   : -8.0   Min.   :-58.00   Min.   :104.0   Min.   :0  
 1st Qu.: 2.000   1st Qu.:116.8   1st Qu.: 51.00   1st Qu.:122.8   1st Qu.:0  
 Median : 6.000   Median :133.0   Median : 72.00   Median :135.5   Median :0  
 Mean   : 6.477   Mean   :139.3   Mean   : 74.29   Mean   :146.2   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:158.2   3rd Qu.: 95.00   3rd Qu.:154.2   3rd Qu.:0  
 Max.   :12.000   Max.   :350.0   Max.   :223.00   Max.   :422.0   Max.   :0  
   prof_nieve         longitud        latitud           altitud      
 Min.   :  0.000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:41.89   1st Qu.: -8.624   1st Qu.:  58.0  
 Median :  0.000   Median :42.43   Median : -8.411   Median : 261.0  
 Mean   :  2.574   Mean   :41.48   Mean   : -6.594   Mean   : 352.7  
 3rd Qu.:  0.000   3rd Qu.:42.89   3rd Qu.: -4.010   3rd Qu.: 370.0  
 Max.   :607.000   Max.   :43.57   Max.   :  2.827   Max.   :2400.0  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt          tmax            tmin            precip     
 Min.   : 4.00   Min.   :  8.0   Min.   :-110.0   Min.   : 0.00  
 1st Qu.: 7.00   1st Qu.:182.0   1st Qu.:  79.0   1st Qu.: 2.00  
 Median : 8.00   Median :237.0   Median : 126.0   Median : 8.00  
 Mean   : 8.45   Mean   :230.5   Mean   : 119.6   Mean   :10.47  
 3rd Qu.:10.00   3rd Qu.:284.0   3rd Qu.: 164.0   3rd Qu.:16.00  
 Max.   :12.00   Max.   :403.0   Max.   : 254.0   Max.   :52.00  
     nevada            prof_nieve          longitud        latitud       
 Min.   :0.0000000   Min.   : 0.00000   Min.   :35.28   Min.   :-8.6494  
 1st Qu.:0.0000000   1st Qu.: 0.00000   1st Qu.:38.95   1st Qu.:-4.8500  
 Median :0.0000000   Median : 0.00000   Median :40.87   Median :-2.7331  
 Mean   :0.0001782   Mean   : 0.01897   Mean   :40.39   Mean   :-2.4887  
 3rd Qu.:0.0000000   3rd Qu.: 0.00000   3rd Qu.:41.96   3rd Qu.: 0.4731  
 Max.   :3.0000000   Max.   :59.00000   Max.   :43.57   Max.   : 4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  44.0  
 Median : 259.5  
 Mean   : 376.0  
 3rd Qu.: 667.0  
 Max.   :1971.0  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt           tmax            tmin           precip            nevada 
 Min.   : 1.000   Min.   : 13.0   Min.   :-33.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 4.000   1st Qu.:201.0   1st Qu.:132.0   1st Qu.:  0.000   1st Qu.:0  
 Median : 7.000   Median :225.0   Median :160.0   Median :  1.000   Median :0  
 Mean   : 6.505   Mean   :217.4   Mean   :150.6   Mean   :  6.999   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:253.0   3rd Qu.:190.0   3rd Qu.:  8.000   3rd Qu.:0  
 Max.   :12.000   Max.   :356.0   Max.   :244.0   Max.   :114.000   Max.   :0  
   prof_nieve          longitud        latitud          altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.89   Min.   :  14.0  
 1st Qu.: 0.00000   1st Qu.:28.31   1st Qu.:-16.50   1st Qu.:  25.0  
 Median : 0.00000   Median :28.44   Median :-16.33   Median :  35.0  
 Mean   : 0.03084   Mean   :28.37   Mean   :-16.05   Mean   : 518.3  
 3rd Qu.: 0.00000   3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.: 632.0  
 Max.   :46.00000   Max.   :28.95   Max.   :-13.60   Max.   :2371.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

Visualización de 8 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=8)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=8)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)
  df.cluster07 <- subset(df, cluster==7)
  df.cluster08 <- subset(df, cluster==8)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster07 <- select(df.cluster07, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster08 <- select(df.cluster08, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax            tmin            precip           nevada 
 Min.   : 1.000   Min.   : 50.0   Min.   :-30.00   Min.   : 34.00   Min.   :0  
 1st Qu.: 3.000   1st Qu.:133.0   1st Qu.: 60.00   1st Qu.: 48.00   1st Qu.:0  
 Median : 9.000   Median :159.0   Median : 83.00   Median : 58.00   Median :0  
 Mean   : 7.442   Mean   :164.9   Mean   : 86.71   Mean   : 61.92   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:193.0   3rd Qu.:111.00   3rd Qu.: 72.00   3rd Qu.:0  
 Max.   :12.000   Max.   :336.0   Max.   :219.00   Max.   :125.00   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   : 0.00000   Min.   :28.48   Min.   :-17.755   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:40.71   1st Qu.: -6.056   1st Qu.:  32.0  
 Median : 0.00000   Median :42.33   Median : -3.799   Median :  95.0  
 Mean   : 0.06001   Mean   :41.48   Mean   : -3.428   Mean   : 205.2  
 3rd Qu.: 0.00000   3rd Qu.:43.31   3rd Qu.: -1.033   3rd Qu.: 334.5  
 Max.   :35.00000   Max.   :43.57   Max.   :  4.216   Max.   :1405.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax            tmin            precip     
 Min.   :1.000   Min.   : -4.0   Min.   :-89.00   Min.   : 0.00  
 1st Qu.:2.000   1st Qu.:128.0   1st Qu.: 28.00   1st Qu.: 5.00  
 Median :3.000   Median :161.0   Median : 61.00   Median :14.00  
 Mean   :2.865   Mean   :161.5   Mean   : 60.56   Mean   :15.92  
 3rd Qu.:4.000   3rd Qu.:191.0   3rd Qu.: 91.00   3rd Qu.:24.00  
 Max.   :9.000   Max.   :355.0   Max.   :236.00   Max.   :87.00  
     nevada           prof_nieve          longitud        latitud      
 Min.   :0.000000   Min.   : 0.00000   Min.   :35.28   Min.   :-8.649  
 1st Qu.:0.000000   1st Qu.: 0.00000   1st Qu.:38.95   1st Qu.:-5.289  
 Median :0.000000   Median : 0.00000   Median :40.95   Median :-2.331  
 Mean   :0.000662   Mean   : 0.09857   Mean   :40.50   Mean   :-2.308  
 3rd Qu.:0.000000   3rd Qu.: 0.00000   3rd Qu.:42.08   3rd Qu.: 0.595  
 Max.   :6.000000   Max.   :75.00000   Max.   :43.57   Max.   : 4.216  
    altitud      
 Min.   :   1.0  
 1st Qu.:  44.0  
 Median : 192.0  
 Mean   : 355.1  
 3rd Qu.: 628.0  
 Max.   :1668.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax             tmin             precip      
 Min.   : 1.00   Min.   :-53.00   Min.   :-121.00   Min.   :  0.00  
 1st Qu.: 4.00   1st Qu.: 29.00   1st Qu.: -33.00   1st Qu.: 17.00  
 Median : 6.00   Median : 73.00   Median :   6.00   Median : 30.00  
 Mean   : 6.51   Mean   : 82.95   Mean   :  12.65   Mean   : 34.91  
 3rd Qu.:10.00   3rd Qu.:133.00   3rd Qu.:  58.00   3rd Qu.: 48.00  
 Max.   :12.00   Max.   :263.00   Max.   : 148.00   Max.   :135.00  
     nevada    prof_nieve         longitud        latitud        
 Min.   :0   Min.   :   0.00   Min.   :28.31   Min.   :-16.4992  
 1st Qu.:0   1st Qu.:   0.00   1st Qu.:40.78   1st Qu.: -4.0103  
 Median :0   Median :   0.00   Median :42.38   Median :  0.8842  
 Mean   :0   Mean   :  14.85   Mean   :41.91   Mean   : -0.4648  
 3rd Qu.:0   3rd Qu.:   0.00   3rd Qu.:42.53   3rd Qu.:  1.3656  
 Max.   :0   Max.   :1834.00   Max.   :42.77   Max.   :  2.4378  
    altitud    
 Min.   :1167  
 1st Qu.:1894  
 Median :2228  
 Mean   :2152  
 3rd Qu.:2316  
 Max.   :2535  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt           tmax            tmin            precip          nevada 
 Min.   : 1.000   Min.   : -8.0   Min.   :-58.00   Min.   :104.0   Min.   :0  
 1st Qu.: 2.000   1st Qu.:117.0   1st Qu.: 50.50   1st Qu.:122.0   1st Qu.:0  
 Median : 6.000   Median :134.0   Median : 72.00   Median :133.0   Median :0  
 Mean   : 6.527   Mean   :137.6   Mean   : 72.93   Mean   :136.2   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:158.5   3rd Qu.: 95.00   3rd Qu.:147.0   3rd Qu.:0  
 Max.   :12.000   Max.   :326.0   Max.   :207.00   Max.   :197.0   Max.   :0  
   prof_nieve         longitud        latitud           altitud      
 Min.   :  0.000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:41.98   1st Qu.: -8.624   1st Qu.:  43.3  
 Median :  0.000   Median :42.43   Median : -8.411   Median : 261.0  
 Mean   :  2.842   Mean   :41.54   Mean   : -6.546   Mean   : 341.7  
 3rd Qu.:  0.000   3rd Qu.:42.89   3rd Qu.: -4.010   3rd Qu.: 370.0  
 Max.   :607.000   Max.   :43.57   Max.   :  2.827   Max.   :2400.0  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt           tmax            tmin           precip     
 Min.   : 4.000   Min.   :  8.0   Min.   :-50.0   Min.   : 0.00  
 1st Qu.: 7.000   1st Qu.:193.0   1st Qu.:100.0   1st Qu.: 2.00  
 Median : 8.000   Median :241.0   Median :142.0   Median : 7.00  
 Mean   : 8.543   Mean   :236.7   Mean   :135.2   Mean   :10.97  
 3rd Qu.:10.000   3rd Qu.:284.0   3rd Qu.:175.0   3rd Qu.:17.00  
 Max.   :12.000   Max.   :403.0   Max.   :254.0   Max.   :52.00  
     nevada            prof_nieve          longitud        latitud       
 Min.   :0.0000000   Min.   : 0.00000   Min.   :35.28   Min.   :-8.6494  
 1st Qu.:0.0000000   1st Qu.: 0.00000   1st Qu.:37.96   1st Qu.:-5.5975  
 Median :0.0000000   Median : 0.00000   Median :41.17   Median :-1.2294  
 Mean   :0.0001858   Mean   : 0.01425   Mean   :40.28   Mean   :-1.9815  
 3rd Qu.:0.0000000   3rd Qu.: 0.00000   3rd Qu.:42.33   3rd Qu.: 0.7106  
 Max.   :3.0000000   Max.   :59.00000   Max.   :43.57   Max.   : 4.2156  
    altitud     
 Min.   :  1.0  
 1st Qu.: 22.0  
 Median : 71.0  
 Mean   :148.4  
 3rd Qu.:247.0  
 Max.   :953.0  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt           tmax            tmin             precip      
 Min.   : 4.000   Min.   :  8.0   Min.   :-110.00   Min.   : 0.000  
 1st Qu.: 6.000   1st Qu.:156.0   1st Qu.:  48.00   1st Qu.: 2.000  
 Median : 8.000   Median :226.5   Median :  95.00   Median : 8.000  
 Mean   : 8.285   Mean   :219.4   Mean   :  91.94   Mean   : 9.599  
 3rd Qu.:10.000   3rd Qu.:284.0   3rd Qu.: 135.00   3rd Qu.:14.000  
 Max.   :12.000   Max.   :400.0   Max.   : 250.00   Max.   :48.000  
     nevada            prof_nieve          longitud        latitud      
 Min.   :0.0000000   Min.   : 0.00000   Min.   :37.13   Min.   :-8.411  
 1st Qu.:0.0000000   1st Qu.: 0.00000   1st Qu.:40.07   1st Qu.:-4.680  
 Median :0.0000000   Median : 0.00000   Median :40.66   Median :-3.764  
 Mean   :0.0001647   Mean   : 0.02734   Mean   :40.59   Mean   :-3.388  
 3rd Qu.:0.0000000   3rd Qu.: 0.00000   3rd Qu.:41.52   3rd Qu.:-2.138  
 Max.   :2.0000000   Max.   :35.00000   Max.   :43.12   Max.   : 2.438  
    altitud      
 Min.   : 370.0  
 1st Qu.: 627.0  
 Median : 735.0  
 Mean   : 779.3  
 3rd Qu.: 916.0  
 Max.   :1971.0  

if (!empty_nodes) summary(df.cluster07)

   fecha_cnt           tmax            tmin           precip            nevada 
 Min.   : 1.000   Min.   : 13.0   Min.   :-33.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 4.000   1st Qu.:201.0   1st Qu.:132.0   1st Qu.:  0.000   1st Qu.:0  
 Median : 7.000   Median :225.0   Median :160.0   Median :  1.000   Median :0  
 Mean   : 6.505   Mean   :217.4   Mean   :150.6   Mean   :  6.999   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:253.0   3rd Qu.:190.0   3rd Qu.:  8.000   3rd Qu.:0  
 Max.   :12.000   Max.   :356.0   Max.   :244.0   Max.   :114.000   Max.   :0  
   prof_nieve          longitud        latitud          altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.89   Min.   :  14.0  
 1st Qu.: 0.00000   1st Qu.:28.31   1st Qu.:-16.50   1st Qu.:  25.0  
 Median : 0.00000   Median :28.44   Median :-16.33   Median :  35.0  
 Mean   : 0.03084   Mean   :28.37   Mean   :-16.05   Mean   : 518.3  
 3rd Qu.: 0.00000   3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.: 632.0  
 Max.   :46.00000   Max.   :28.95   Max.   :-13.60   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster08)

   fecha_cnt       tmax            tmin            precip          nevada 
 Min.   : 1   Min.   : 37.0   Min.   :-11.00   Min.   :191.0   Min.   :0  
 1st Qu.: 2   1st Qu.:115.0   1st Qu.: 63.00   1st Qu.:209.0   1st Qu.:0  
 Median : 4   Median :125.0   Median : 75.00   Median :227.0   Median :0  
 Mean   : 6   Mean   :154.7   Mean   : 87.27   Mean   :242.8   Mean   :0  
 3rd Qu.:10   3rd Qu.:156.0   3rd Qu.: 92.00   3rd Qu.:252.0   3rd Qu.:0  
 Max.   :12   Max.   :350.0   Max.   :223.00   Max.   :422.0   Max.   :0  
   prof_nieve    longitud        latitud           altitud      
 Min.   :0    Min.   :28.31   Min.   :-16.499   Min.   :   4.0  
 1st Qu.:0    1st Qu.:41.67   1st Qu.: -8.624   1st Qu.: 261.0  
 Median :0    Median :42.24   Median : -8.411   Median : 263.0  
 Mean   :0    Mean   :40.94   Mean   : -7.051   Mean   : 459.1  
 3rd Qu.:0    3rd Qu.:42.89   3rd Qu.: -3.174   3rd Qu.: 370.0  
 Max.   :0    Max.   :43.36   Max.   :  2.825   Max.   :2371.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1], dim(df.cluster07)[1], dim(df.cluster08)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06", "cluster07", "cluster08"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.hist(df.cluster07)

if (!empty_nodes) mpr.hist(df.cluster08)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster07)

if (!empty_nodes) mpr.boxplot(df.cluster08)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
  df.cluster07.grouped <- mpr.group_by_geo(df.cluster07)
  df.cluster08.grouped <- mpr.group_by_geo(df.cluster08)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster07.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster08.grouped)

Visualización de 10 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=10)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=10)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)
  df.cluster07 <- subset(df, cluster==7)
  df.cluster08 <- subset(df, cluster==8)
  df.cluster09 <- subset(df, cluster==9)
  df.cluster10 <- subset(df, cluster==10)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster07 <- select(df.cluster07, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster08 <- select(df.cluster08, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster09 <- select(df.cluster09, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster10 <- select(df.cluster10, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt         tmax            tmin            precip           nevada 
 Min.   :1.00   Min.   : 50.0   Min.   :-22.00   Min.   : 34.00   Min.   :0  
 1st Qu.:2.00   1st Qu.:127.0   1st Qu.: 54.00   1st Qu.: 47.00   1st Qu.:0  
 Median :3.00   Median :150.0   Median : 72.00   Median : 57.00   Median :0  
 Mean   :2.93   Mean   :154.2   Mean   : 74.01   Mean   : 60.06   Mean   :0  
 3rd Qu.:4.00   3rd Qu.:176.0   3rd Qu.: 93.00   3rd Qu.: 70.00   3rd Qu.:0  
 Max.   :7.00   Max.   :301.0   Max.   :186.00   Max.   :115.00   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   : 0.00000   Min.   :35.28   Min.   :-8.6494   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:41.29   1st Qu.:-5.6156   1st Qu.:  29.0  
 Median : 0.00000   Median :42.44   Median :-2.6544   Median :  90.0  
 Mean   : 0.06496   Mean   :41.77   Mean   :-2.6710   Mean   : 157.5  
 3rd Qu.: 0.00000   3rd Qu.:43.31   3rd Qu.: 0.4914   3rd Qu.: 251.0  
 Max.   :35.00000   Max.   :43.57   Max.   : 4.2156   Max.   :1055.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax            tmin            precip     
 Min.   :1.000   Min.   : -4.0   Min.   :-89.00   Min.   : 0.00  
 1st Qu.:2.000   1st Qu.:128.0   1st Qu.: 28.00   1st Qu.: 5.00  
 Median :3.000   Median :161.0   Median : 61.00   Median :14.00  
 Mean   :2.865   Mean   :161.5   Mean   : 60.56   Mean   :15.92  
 3rd Qu.:4.000   3rd Qu.:191.0   3rd Qu.: 91.00   3rd Qu.:24.00  
 Max.   :9.000   Max.   :355.0   Max.   :236.00   Max.   :87.00  
     nevada           prof_nieve          longitud        latitud      
 Min.   :0.000000   Min.   : 0.00000   Min.   :35.28   Min.   :-8.649  
 1st Qu.:0.000000   1st Qu.: 0.00000   1st Qu.:38.95   1st Qu.:-5.289  
 Median :0.000000   Median : 0.00000   Median :40.95   Median :-2.331  
 Mean   :0.000662   Mean   : 0.09857   Mean   :40.50   Mean   :-2.308  
 3rd Qu.:0.000000   3rd Qu.: 0.00000   3rd Qu.:42.08   3rd Qu.: 0.595  
 Max.   :6.000000   Max.   :75.00000   Max.   :43.57   Max.   : 4.216  
    altitud      
 Min.   :   1.0  
 1st Qu.:  44.0  
 Median : 192.0  
 Mean   : 355.1  
 3rd Qu.: 628.0  
 Max.   :1668.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax             tmin             precip      
 Min.   : 1.00   Min.   :-53.00   Min.   :-121.00   Min.   :  0.00  
 1st Qu.: 4.00   1st Qu.: 29.00   1st Qu.: -33.00   1st Qu.: 17.00  
 Median : 6.00   Median : 73.00   Median :   6.00   Median : 30.00  
 Mean   : 6.51   Mean   : 82.95   Mean   :  12.65   Mean   : 34.91  
 3rd Qu.:10.00   3rd Qu.:133.00   3rd Qu.:  58.00   3rd Qu.: 48.00  
 Max.   :12.00   Max.   :263.00   Max.   : 148.00   Max.   :135.00  
     nevada    prof_nieve         longitud        latitud        
 Min.   :0   Min.   :   0.00   Min.   :28.31   Min.   :-16.4992  
 1st Qu.:0   1st Qu.:   0.00   1st Qu.:40.78   1st Qu.: -4.0103  
 Median :0   Median :   0.00   Median :42.38   Median :  0.8842  
 Mean   :0   Mean   :  14.85   Mean   :41.91   Mean   : -0.4648  
 3rd Qu.:0   3rd Qu.:   0.00   3rd Qu.:42.53   3rd Qu.:  1.3656  
 Max.   :0   Max.   :1834.00   Max.   :42.77   Max.   :  2.4378  
    altitud    
 Min.   :1167  
 1st Qu.:1894  
 Median :2228  
 Mean   :2152  
 3rd Qu.:2316  
 Max.   :2535  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt           tmax            tmin            precip          nevada 
 Min.   : 1.000   Min.   : -8.0   Min.   :-58.00   Min.   :104.0   Min.   :0  
 1st Qu.: 2.000   1st Qu.:117.0   1st Qu.: 50.50   1st Qu.:122.0   1st Qu.:0  
 Median : 6.000   Median :134.0   Median : 72.00   Median :133.0   Median :0  
 Mean   : 6.527   Mean   :137.6   Mean   : 72.93   Mean   :136.2   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:158.5   3rd Qu.: 95.00   3rd Qu.:147.0   3rd Qu.:0  
 Max.   :12.000   Max.   :326.0   Max.   :207.00   Max.   :197.0   Max.   :0  
   prof_nieve         longitud        latitud           altitud      
 Min.   :  0.000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:41.98   1st Qu.: -8.624   1st Qu.:  43.3  
 Median :  0.000   Median :42.43   Median : -8.411   Median : 261.0  
 Mean   :  2.842   Mean   :41.54   Mean   : -6.546   Mean   : 341.7  
 3rd Qu.:  0.000   3rd Qu.:42.89   3rd Qu.: -4.010   3rd Qu.: 370.0  
 Max.   :607.000   Max.   :43.57   Max.   :  2.827   Max.   :2400.0  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt           tmax            tmin           precip     
 Min.   : 4.000   Min.   :  8.0   Min.   :-50.0   Min.   : 0.00  
 1st Qu.: 7.000   1st Qu.:193.0   1st Qu.:100.0   1st Qu.: 2.00  
 Median : 8.000   Median :241.0   Median :142.0   Median : 7.00  
 Mean   : 8.543   Mean   :236.7   Mean   :135.2   Mean   :10.97  
 3rd Qu.:10.000   3rd Qu.:284.0   3rd Qu.:175.0   3rd Qu.:17.00  
 Max.   :12.000   Max.   :403.0   Max.   :254.0   Max.   :52.00  
     nevada            prof_nieve          longitud        latitud       
 Min.   :0.0000000   Min.   : 0.00000   Min.   :35.28   Min.   :-8.6494  
 1st Qu.:0.0000000   1st Qu.: 0.00000   1st Qu.:37.96   1st Qu.:-5.5975  
 Median :0.0000000   Median : 0.00000   Median :41.17   Median :-1.2294  
 Mean   :0.0001858   Mean   : 0.01425   Mean   :40.28   Mean   :-1.9815  
 3rd Qu.:0.0000000   3rd Qu.: 0.00000   3rd Qu.:42.33   3rd Qu.: 0.7106  
 Max.   :3.0000000   Max.   :59.00000   Max.   :43.57   Max.   : 4.2156  
    altitud     
 Min.   :  1.0  
 1st Qu.: 22.0  
 Median : 71.0  
 Mean   :148.4  
 3rd Qu.:247.0  
 Max.   :953.0  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt           tmax            tmin             precip      
 Min.   : 4.000   Min.   :  8.0   Min.   :-110.00   Min.   : 0.000  
 1st Qu.: 6.000   1st Qu.:156.0   1st Qu.:  48.00   1st Qu.: 2.000  
 Median : 8.000   Median :226.5   Median :  95.00   Median : 8.000  
 Mean   : 8.285   Mean   :219.4   Mean   :  91.94   Mean   : 9.599  
 3rd Qu.:10.000   3rd Qu.:284.0   3rd Qu.: 135.00   3rd Qu.:14.000  
 Max.   :12.000   Max.   :400.0   Max.   : 250.00   Max.   :48.000  
     nevada            prof_nieve          longitud        latitud      
 Min.   :0.0000000   Min.   : 0.00000   Min.   :37.13   Min.   :-8.411  
 1st Qu.:0.0000000   1st Qu.: 0.00000   1st Qu.:40.07   1st Qu.:-4.680  
 Median :0.0000000   Median : 0.00000   Median :40.66   Median :-3.764  
 Mean   :0.0001647   Mean   : 0.02734   Mean   :40.59   Mean   :-3.388  
 3rd Qu.:0.0000000   3rd Qu.: 0.00000   3rd Qu.:41.52   3rd Qu.:-2.138  
 Max.   :2.0000000   Max.   :35.00000   Max.   :43.12   Max.   : 2.438  
    altitud      
 Min.   : 370.0  
 1st Qu.: 627.0  
 Median : 735.0  
 Mean   : 779.3  
 3rd Qu.: 916.0  
 Max.   :1971.0  

if (!empty_nodes) summary(df.cluster07)

   fecha_cnt           tmax            tmin           precip            nevada 
 Min.   : 1.000   Min.   : 87.0   Min.   : 64.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 3.000   1st Qu.:212.0   1st Qu.:150.0   1st Qu.:  0.000   1st Qu.:0  
 Median : 6.000   Median :233.0   Median :168.0   Median :  1.000   Median :0  
 Mean   : 6.488   Mean   :233.9   Mean   :169.4   Mean   :  6.329   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:259.0   3rd Qu.:196.0   3rd Qu.:  7.000   3rd Qu.:0  
 Max.   :12.000   Max.   :356.0   Max.   :244.0   Max.   :103.000   Max.   :0  
   prof_nieve           longitud        latitud          altitud     
 Min.   :0.0000000   Min.   :27.82   Min.   :-17.89   Min.   : 14.0  
 1st Qu.:0.0000000   1st Qu.:28.05   1st Qu.:-16.56   1st Qu.: 25.0  
 Median :0.0000000   Median :28.46   Median :-16.26   Median : 33.0  
 Mean   :0.0003517   Mean   :28.38   Mean   :-15.96   Mean   :131.3  
 3rd Qu.:0.0000000   3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.: 64.0  
 Max.   :2.0000000   Max.   :28.95   Max.   :-13.60   Max.   :632.0  

if (!empty_nodes) summary(df.cluster08)

   fecha_cnt          tmax            tmin            precip           nevada 
 Min.   : 6.00   Min.   : 53.0   Min.   :-30.00   Min.   : 34.00   Min.   :0  
 1st Qu.:10.00   1st Qu.:137.2   1st Qu.: 67.00   1st Qu.: 49.00   1st Qu.:0  
 Median :11.00   Median :170.0   Median : 94.00   Median : 58.00   Median :0  
 Mean   :10.67   Mean   :172.5   Mean   : 95.78   Mean   : 63.25   Mean   :0  
 3rd Qu.:12.00   3rd Qu.:205.0   3rd Qu.:124.00   3rd Qu.: 74.00   3rd Qu.:0  
 Max.   :12.00   Max.   :336.0   Max.   :219.00   Max.   :125.00   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   : 0.00000   Min.   :28.48   Min.   :-17.755   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:39.95   1st Qu.: -6.829   1st Qu.:  34.0  
 Median : 0.00000   Median :42.33   Median : -3.831   Median : 108.0  
 Mean   : 0.05647   Mean   :41.27   Mean   : -3.969   Mean   : 239.2  
 3rd Qu.: 0.00000   3rd Qu.:43.31   3rd Qu.: -1.787   3rd Qu.: 370.0  
 Max.   :27.00000   Max.   :43.57   Max.   :  4.216   Max.   :1405.0  

if (!empty_nodes) summary(df.cluster09)

   fecha_cnt           tmax            tmin            precip           nevada 
 Min.   : 1.000   Min.   : 13.0   Min.   :-33.00   Min.   :  0.00   Min.   :0  
 1st Qu.: 4.000   1st Qu.: 94.0   1st Qu.: 23.00   1st Qu.:  0.00   1st Qu.:0  
 Median : 7.000   Median :129.0   Median : 51.00   Median :  3.00   Median :0  
 Mean   : 6.582   Mean   :138.4   Mean   : 60.86   Mean   : 10.21   Mean   :0  
 3rd Qu.: 9.250   3rd Qu.:183.0   3rd Qu.: 98.25   3rd Qu.: 13.00   3rd Qu.:0  
 Max.   :12.000   Max.   :253.0   Max.   :159.00   Max.   :114.00   Max.   :0  
   prof_nieve         longitud        latitud         altitud    
 Min.   : 0.0000   Min.   :28.31   Min.   :-16.5   Min.   :2371  
 1st Qu.: 0.0000   1st Qu.:28.31   1st Qu.:-16.5   1st Qu.:2371  
 Median : 0.0000   Median :28.31   Median :-16.5   Median :2371  
 Mean   : 0.1768   Mean   :28.31   Mean   :-16.5   Mean   :2371  
 3rd Qu.: 0.0000   3rd Qu.:28.31   3rd Qu.:-16.5   3rd Qu.:2371  
 Max.   :46.0000   Max.   :28.31   Max.   :-16.5   Max.   :2371  

if (!empty_nodes) summary(df.cluster10)

   fecha_cnt       tmax            tmin            precip          nevada 
 Min.   : 1   Min.   : 37.0   Min.   :-11.00   Min.   :191.0   Min.   :0  
 1st Qu.: 2   1st Qu.:115.0   1st Qu.: 63.00   1st Qu.:209.0   1st Qu.:0  
 Median : 4   Median :125.0   Median : 75.00   Median :227.0   Median :0  
 Mean   : 6   Mean   :154.7   Mean   : 87.27   Mean   :242.8   Mean   :0  
 3rd Qu.:10   3rd Qu.:156.0   3rd Qu.: 92.00   3rd Qu.:252.0   3rd Qu.:0  
 Max.   :12   Max.   :350.0   Max.   :223.00   Max.   :422.0   Max.   :0  
   prof_nieve    longitud        latitud           altitud      
 Min.   :0    Min.   :28.31   Min.   :-16.499   Min.   :   4.0  
 1st Qu.:0    1st Qu.:41.67   1st Qu.: -8.624   1st Qu.: 261.0  
 Median :0    Median :42.24   Median : -8.411   Median : 263.0  
 Mean   :0    Mean   :40.94   Mean   : -7.051   Mean   : 459.1  
 3rd Qu.:0    3rd Qu.:42.89   3rd Qu.: -3.174   3rd Qu.: 370.0  
 Max.   :0    Max.   :43.36   Max.   :  2.825   Max.   :2371.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1], dim(df.cluster07)[1], dim(df.cluster08)[1], dim(df.cluster09)[1], dim(df.cluster10)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06", "cluster07", "cluster08", "cluster09", "cluster10"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.hist(df.cluster07)

if (!empty_nodes) mpr.hist(df.cluster08)

if (!empty_nodes) mpr.hist(df.cluster09)

if (!empty_nodes) mpr.hist(df.cluster10)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster07)

if (!empty_nodes) mpr.boxplot(df.cluster08)

if (!empty_nodes) mpr.boxplot(df.cluster09)

if (!empty_nodes) mpr.boxplot(df.cluster10)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
  df.cluster07.grouped <- mpr.group_by_geo(df.cluster07)
  df.cluster08.grouped <- mpr.group_by_geo(df.cluster08)
  df.cluster09.grouped <- mpr.group_by_geo(df.cluster09)
  df.cluster10.grouped <- mpr.group_by_geo(df.cluster10)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster07.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster08.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster09.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster10.grouped)